Model Anatomy See what's inside open-weight AI models

Can I run gemma-4-31B-it-AWQ on an RTX 6000 Ada?

Yes

Its published weights (20.5 GB) fit in the 43.2 GB an RTX 6000 Ada can use, with room for ≈ 131K tokens of context.

Full analysis of gemma-4-31B-it-AWQ Everything that runs on RTX 6000 Ada Get the weights on Hugging Face
hf download QuantTrio/gemma-4-31B-it-AWQ

Files and context on RTX 6000 Ada

Each file of gemma-4-31B-it-AWQ (and of GGUF versions the site has analyzed), and how much context fits next to it, with the context cache in 16-bit or 8-bit.

FileSizeOn RTX 6000 Ada Context (16-bit)Context (8-bit)
As published20.5 GBFits131K256K
4-bit (estimate)17.6 GBFits148K256K

gemma-4-31B-it-AWQ on other hardware

Popular models that run on RTX 6000 Ada

Assumes 90% of the card's memory is usable and at least 4K tokens of context for one conversation, with the context cache in 16-bit unless noted. Fits leaves at least 20% of that memory for context; Tight leaves less.